Farming MadeEasy

Recommends optimum crops to be cultivated based on soil properties and weather conditions

Comment

Inspiration

Earlier, crop cultivation was undertaken based on farmers’ hands-on expertise. However, climate change has begun to affect crop yields badly. Consequently, farmers are unable to choose the right crops based on soil and environmental factors, and the process of manually predicting the choice of the right crops of land has, more often than not, failed. Accurate crop prediction results in increased crop production.

Precision agriculture is in trend nowadays. Precision agriculture is a modern farming technique that uses the data of soil characteristics, soil types, crop yield data, and weather conditions and suggests to the farmers the most optimal crop to grow on their farms for maximum yield and profit. This technique can reduce crop failures and help farmers make informed decisions about their farming strategy.

In order to mitigate the agrarian crisis in the current status quo, there is a need for better recommendation systems to alleviate the problem by helping the farmers to make an informed decision before starting the cultivation of crops.

Precision Farming Market cap

What it does

Farming MadeEasy is an easy-to-use web platform developed powered by the SingleStore DB for the farmer to predict the better suitable crop for a particular location. The key features are:

  1. Recommend the user the optimal crop to cultivate based on several parameters for given soil and weather conditions.
  2. Provide easy usage to one seamless user interface powered by an interactive open-source map to easily navigate to the desired location.

How we built it

  1. Machine Learning Model: To construct the machine learning model for our project, we used the hyperparameter optimization method to find the right combination of hyperparameter values for the random forest classifier model to achieve maximum prediction accuracy on the data in a reasonable amount of time. The dataset provides a label for the optimal crop based on the Nitrogen, Phosphorous, Potassium, Temperature, Humidity, pH, and Rainfall levels that are observed in the environment. There are a total of 22 possible crop labels in the dataset.

  2. Crop Recommendation API: The machine learning model trained on the SingleStore DB is saved for future predictions and deployed with the help of the serverless function on the azure function app as an HTTP endpoint. It provides great flexibility to utilize the endpoints in the web or mobile application.

  3. Web Portal: The client interface of the application is developed using react. Where we have provided the Map from where Farmers can select the land where they want to see the predictions on the basis of the geo-coordinates. Furthermore, this application fetches the soil properties from the IRSIC - World soil information database & weather conditions such as temperature, relative humidity, and average precipitation from the weatherBit Historical API. All these cumulative parameters get passed to the crop recommendation API to get the most suitable crop for provided the conditions. Architecture Diagram

Challenges we ran into

We ran into one major challenge in finding the right agricultural dataset with the appropriate agricultural properties.

Accomplishments that we're proud of

We are proud of implementing a fully-functioning interactive map and suggestions for farmers to cultivate the most optimal crop at a location, also building a solution that could potentially solve a global crisis of food scarcity.

What we learned

Through this project, we learn how to leverage the SingleStore database for AI/ML applications that require large and fast data processing. We also learn the process of developing a serverless application. This project can’t be done without the efforts and collaboration of a team with diverse backgrounds in technical skills.

What's next for Farming MadeEasy

We will find a larger crop dataset so the application can be more precise and widely used! Also, we would also like to integrate several other features that provide more relevant insight into land use for farmers.

Share this project:

Updates